Engineering Risk Monitoring System and Method Based on State Transition

A technology of state transfer and risk monitoring, which is applied in engineering risk monitoring system, engineering risk monitoring system based on state transfer, and engineering risk monitoring field based on state transfer, can solve the problems that cannot be targeted to solve the uncertainties and emergencies of underground engineering disasters Issues such as frequent occurrence, inability to capture the precursors of unknown disasters, different sampling frequencies, insufficient high-dimensional and massive information, etc.

Inactive Publication Date: 2016-12-28
SHANGHAI UNIV +1
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] However, the above three types of underground engineering risk analysis methods cannot specifically solve the uncertain and sudden problems of underground engineering disasters, and cannot capture the precursors of unknown disasters
The above methods are far from enough for the utilization of high-dimensional and massive information with different sampling frequencies and scales

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Engineering Risk Monitoring System and Method Based on State Transition
  • Engineering Risk Monitoring System and Method Based on State Transition
  • Engineering Risk Monitoring System and Method Based on State Transition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0154] see figure 1 , The present invention discloses an engineering risk monitoring system based on state transition, said system comprising: a raw data processing module, a state transition visualization expression module, a graphic feature extraction module, an automatic learning module, and an automatic image recognition module.

[0155]The original data processing module is used to obtain the original data, and process the original data through dimensionless processing. The state transition visualization expression module is connected with the original data processing module, and is used to generate a state transition diagram of each state in the project according to the data processed by the original data processing module. The graphical feature extraction module is connected with the state transition visualization expression module to obtain the state transition diagram generated by the state transition visualization expression module, and extract the set features of th...

Embodiment 2

[0275] The present invention takes the Yangtze River Tunnel Project as an example to illustrate the application effect of the method.

[0276] There are many dimensions of data collected in real time throughout the Yangtze River Tunnel. This experiment uses the five-dimensional pressure value of the shield sealed cabin for risk prediction. Table 1 illustrates the basic information of the Yangtze River Tunnel Engineering Experiment. In the experiment, a total of 10,563 pieces of cabin pressure data from the upstream line of the Yangtze River Tunnel from 0:02 am on May 1, 2008 to 5:42 pm on May 22, 2008 were selected as data samples, and the sampling interval was 3 minutes.

[0277] Table 1. Basic information of the Yangtze River Tunnel Experiment

[0278]

[0279] In the experiment, every 240 records are used as a cycle to draw a state transition diagram, and the step interval between the next diagram and the previous diagram is 5, and a total of 2068 state transition diagr...

Embodiment 3

[0285] The difference between this embodiment and Embodiment 1 is that in this embodiment, the state transition visualization expression module adopts a concentric semicircular coordinate system to establish and express multi-dimensional plane coordinates, and the process is as follows:

[0286] N-dimensional Euclidean space R N The concentric semicircular coordinate system consists of N equidistant concentric semicircular coordinate axes. Each semicircle is a coordinate axis, and each axis corresponds to a component of a cube, starting from the center of the circle and numbered from inside to outside: d 0 , d 1 ,...,d i ,...,d N , the central angle of a single peripheral axis ranges from 0 to 180°, increasing in the counterclockwise direction;

[0287] Assume that the i-th component of an N-dimensional time series data at time k is Convert the mapping to a point on the i-th axis through the functions of formula 1 and formula 2 Start from the center of the circle and c...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an engineering risk monitoring system and method based on state transition. The system comprises an initial data processing module, a state transition visualization expression module, an image feature extraction module, an automatic learning module and an automatic image identification module, wherein the state transition visualization expression module is used for generating a state transition diagram of all states in an engineering according to data processed by the initial data processing module; the image feature extraction module is used for extracting set features from the state transition diagram; the automatic learning module is used for calculating ratio of each characteristic value to a historical average value and setting a threshold value according to the extracted features the diagram; the automatic image identification module is used for extracting setting feature of t he state transition diagram according to the image feature extraction module and judging whether the engineering is in a risk state or not according to the threshold value set by the automatic learning module. According to the system and the method provided by the invention, the problems of indeterminateness and uncertainty of underground engineering disasters can be effectively solved, and the risks of the engineering can be visually and automatically monitored, so that the intuition and intelligence are realized.

Description

technical field [0001] The invention belongs to the technical field of computer and measurement, and relates to an engineering risk monitoring system, in particular to an engineering risk monitoring system based on state transition; meanwhile, the invention also relates to an engineering risk monitoring method based on state transition. Background technique [0002] Due to the particularity of underground engineering structures and construction methods, especially the uncertainty and complexity of the surrounding environment (medium) during construction and excavation, it is very difficult to establish an accurate mathematical model for disaster analysis and early warning. Common underground engineering safety analysis methods include the following three categories: [0003] (1) Qualitative risk assessment [0004] Qualitative-based risk analysis techniques (or combined with partial quantitative calculations) are commonly used in the field of risk assessment to determine ri...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06Q10/06
Inventor 胡珉孙瑜峰周文波
Owner SHANGHAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products